Common domain shift problem formulations consider the integration of multiple source domains, or the target domain during training. Regarding the generalization of machine learning models between different car interiors, we formulate the criterion of training in a single vehicle: without access to the target distribution of the vehicle the model would be deployed to, neither with access to multiple vehicles during training. We performed an investigation on the SVIRO dataset for occupant classification on the rear bench and propose an autoencoder based approach to improve the transferability. The autoencoder is on par with commonly used classification models when trained from scratch and sometimes out-performs models pre-trained on a large amount of data. Moreover, the autoencoder can transform images from unknown vehicles into the vehicle it was trained on. These results are corroborated by an evaluation on real infrared images from two vehicle interiors.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Autoencoder Based Inter-Vehicle Generalization for In-Cabin Occupant Classification


    Contributors:


    Publication date :

    2021-07-11


    Size :

    3633692 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    AUTOENCODER BASED INTER-VEHICLE GENERALIZATION FOR IN-CABIN OCCUPANT CLASSIFICATION

    Da Cruz, Steve Dias / Taetz, Bertram / Wasenmüller, Oliver et al. | British Library Conference Proceedings | 2021


    Artificial Intelligence-based Vehicle In-Cabin Occupant Detection and Classification System

    Tamizharasan, M. / Lakshmikanthan, C. | Springer Verlag | 2022


    SYSTEMS AND METHODS FOR VEHICLE OCCUPANT CLASSIFICATION USING IN-CABIN SENSING

    CONG SHAN | European Patent Office | 2024

    Free access

    IN-CABIN OCCUPANT AGE DETERMINATION

    ROBERTS SIMON P / GAGE SERGEI I / DING YANG et al. | European Patent Office | 2023

    Free access

    In-cabin occupant behavoir description

    HU ZILONG / ZHANG LEI / GU QUN | European Patent Office | 2024

    Free access